Byeonggeun Kim

Senior Applied Scientist at Amazon AGI

Personal email: bungkun1349 at gmail dot com

I currently serve as a Senior Applied Scientist at Amazon AGI (Artificial General Intelligence), where I specialize in developing audio foundation models for integration into multi-modal LLMs. In addition, I act as the technical lead for our audio generation solutions. Prior to my tenure at Amazon, I dedicated five years as a Staff Machine learning Researcher at Qualcomm AI Research. My work there centered on advancing wake-word detection and audio event classification, with a focus on efficient architectural design, domain generalization, and few-shot open-set recognition. My current research interests lies at the general machine learning/ deep learning, with a particular emphasis on creating video or text conditioned audio generation solutions for MLLMs.

WORK EXPERIENCE

Amazon AGI (Artificial General Intelligence) Feb 2023 - Present, Seattle, WA, United States

Senior Applied Scientist Apr 2025 - Present

Applied Scientist Ⅱ Feb 2023 - Mar 2025

Feb 2023 - Jul 2024 , Toronto, ON, Canada

Qualcomm AI Research Apr 2018 - Jan 2023, Seoul, South Korea

Staff AI Researcher Nov 2022 - Jan 2023

Senior AI Researcher Dec 2019 - Nov 2022

AI Researcher Apr 2018 - Nov 2019

PUBLICATIONS & PATENTS

Please refer to Publications & Patents page.

Honors

Alexa Perceptual Technology Award Q3/Q4 2023, Recognized for contribution to Large Language Models that raise the functional bar. Awarded by Amazon in Feb 2024.

Byeonggeun Kim

Challenge Winner, IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE) Challenge, DCASE Challenge, 2021 [Results]

Byeonggeun Kim, Seunghan Yang, Jangho Kim, Simyung Chang

Academic Services

Session Chair: INTERSPEECH (2022)

Reviewer: INTERSPEECH (2023-2025), ICASSP (2023-2025), CVPR (2024, 2025), ICCV (2025), WACV (2025, 2026), ACL (2025), AAAI (2025-2026), EMNLP (2025),